self.p = nn.Softmax(dim=1)(torch.mm(self.q.t(), self.H)) # (1*m)
self.u = torch.mul(self.p, self.H).sum(dim=1).unsqueeze(1) # (64*1)
# self.unit_params('R', dim=1)
self.ans_vector = torch.mm(
self.params['R'],
nn.Sigmoid()(self.q + torch.mm(self.params['K'], self.u))) # (k,1)
self.ans = nn.LogSoftmax(dim=1)(self.ans_vector.t())
return self.ans
#--------------------------------------------------------------------------------------------------#
#--------------------------------------------------------------------------------------------------#
#--------------------------------------------------------------------------------------------------#
model = Test_entNet_Model()
CG = graph.Computation_Graph()
fake_sentence = nn.init.normal_(torch.empty(input_size,
dtype=torch.float,
device='cuda'),
mean=0.0,
std=0.1)
fake_question = nn.init.normal_(torch.empty(input_size,
dtype=torch.float,
device='cuda'),
mean=0.0,
std=0.1)
model(fake_sentence)
# ans = model(fake_sentence, fake_question)
ans = model.answer(fake_question)
CG.recursive_loop(ans.grad_fn)
self.p = nn.Softmax(dim=1)(torch.mm(self.q.t(), self.H)) # (1*m)
self.u = torch.mul(self.p, self.H).sum(dim=1).unsqueeze(1) # (64*1)
# self.unit_params('R', dim=1)
self.ans_vector = torch.mm(
self.params['R'],
nn.Sigmoid()(self.q + torch.mm(self.params['K'], self.u))) # (k,1)
self.ans = nn.LogSoftmax(dim=1)(self.ans_vector.t())
return self.ans
#--------------------------------------------------------------------------------------------------#
#--------------------------------------------------------------------------------------------------#
#--------------------------------------------------------------------------------------------------#
model = Test_entNet_Model()
CG = graph.Computation_Graph(identity_size, plot_graph=True)
fake_sentences = [
nn.init.normal_(torch.empty(identity_size['E'],
dtype=torch.float,
requires_grad=True,
device='cuda'),
mean=0.0,
std=0.1).view(input_size) for _ in range(6)
]
fake_question = nn.init.normal_(torch.empty(identity_size['Q'],
dtype=torch.float,
requires_grad=True,
device='cuda'),
mean=0.0,
std=0.1).view(input_size)